Keep reset and schema rewards inside unit interval

Keep grader rewards strictly within unit interval

Harden grader edge cases and packaging metadata

Expand benchmark dataset to 108 incidents

Harden inference transport and output handling

Fix evaluation reliability and lifecycle issues

Change dotenv

Add playground triage brief cards

Align task card content

Remove API note callout

Refine live snapshot cards

Fix home card spacing

Polish UI and add API explorer

Fix submission review issues

Add Hugging Face Space metadata

Merge pull request #2 from ADITYAGABA1322/development

Change Readme.md

Initial SetUp Fixed

Merge pull request #1 from ADITYAGABA1322/development

FIX: improve some structure and added env variables

Added core functionallity

Initial SetUp

Initial SetUp